RT Journal Article
T1 Barrier Height Prediction by Machine Learning Correction of Semiempirical Calculations
A1 García-Andrade, Xabier
A1 García Tahoces, Pablo
A1 Pérez-Ríos, Jesús
A1 Martínez Núñez, Emilio
AB Different machine learning (ML) models are proposed in the present work to predict density functional theory-quality barrier heights (BHs) from semiempirical quantum mechanical (SQM) calculations. The ML models include a multitask deep neural network, gradient-boosted trees by means of the XGBoost interface, and Gaussian process regression. The obtained mean absolute errors are similar to those of previous models considering the same number of data points. The ML corrections proposed in this paper could be useful for rapid screening of the large reaction networks that appear in combustion chemistry or in astrochemistry. Finally, our results show that 70% of the features with the highest impact on model output are bespoke predictors. This custom-made set of predictors could be employed by future Δ-ML models to improve the quantitative prediction of other reaction properties.
PB American Chemical Society
SN 1089-5639
YR 2023
FD 2023
LK http://hdl.handle.net/10347/33825
UL http://hdl.handle.net/10347/33825
LA eng
NO Xabier García-Andrade, Pablo García Tahoces, Jesús Pérez-Ríos and Emilio Martínez Núñez. Barrier Height Prediction by Machine Learning Correction of Semiempirical Calculations. J. Phys. Chem. A 2023, 127, 10, 2274–2283
NO This work was partially supported by Consellería de Cultura, Educación e Ordenación Universitaria (Grupo de referencia competitiva ED431C 2021/40) and by Ministerio de Ciencia e Innovación through Grant #PID2019-107307RB-I00. J.P.-R. acknowledges the support of the Simons Foundation.
DS Minerva
RD 24 abr 2026